When finding the minimax procedures, sometimes the desired prior distribution might not necessarily put the point mass at the boundary of 2. To illustrate this, let us consider the setting of Problem 2 with a single Bernoulli random variable X, but now we assume that the domain of 0 is 2 = [, ]. Find the minimax estimator of 0 under the squared error loss function L(0, d) = (0 - d)2 when 2 = [, g]. For that purpose, let us consider two kinds of Bayesian procedures. (a) Assume that 0 has a prior distribution on two endpoints of 2 with probability mass function Ta(0 = ) = = and Ta(0 = 9) = 2. For the corresponding Bayes procedure, denoted by da, show that its Bayes risk TS (Ta)